visual-to-text

Generate structured user stories from Figma, PDF, or image UI designs.

2|2|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/accionlabs/breezeai-claude-plugin --skill visual-to-text
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: visual-to-text
Source: https://github.com/accionlabs/breezeai-claude-plugin/tree/main/skills/visual-to-text
Command: npx skills add https://github.com/accionlabs/breezeai-claude-plugin --skill visual-to-text

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Transform visual UI designs into structured, actionable user stories, eliminating manual interpretation and ensuring alignment with functional graphs.

Core Features & Use Cases

  • Extract functional intent from Figma URLs, PDFs, or image files.
  • Generate hierarchical personas, outcomes, scenarios, steps, and actions in Markdown.
  • Ideal for product teams converting design mockups into ready-to-implement user stories.

Quick Start

Generate user stories from the Figma design at https://www.figma.com/file/abc123.

Frequently Asked Questions about visual-to-text

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate user stories from Figma designs?

Generate user stories from Figma designs by submitting the frame URL to extract functional intent. The tool reads the visual UI and outputs structured Markdown detailing personas, outcomes, scenarios, steps, and actions aligned with a functional graph.

Can I extract user stories from PDF screens or image files?

You can extract user stories from PDF screens or image files by uploading them directly. The tool processes the visual UI elements to identify scenarios and steps, producing structured Markdown user stories without needing the original design source.

What is a functional graph in UI design analysis?

A functional graph in UI design analysis is a hierarchical structure mapping personas to outcomes, scenarios, steps, and actions. It guides the extraction of functional intent from visuals to ensure generated user stories align with intended product behavior.

Does this visual-to-text tool work with PDF and image formats?

Yes, the tool works with PDF and image formats alongside Figma frames. It reads these visual design files to extract functional intent, requiring no additional dependencies to process the visual inputs into structured Markdown user stories.

How to convert UI mockups into actionable user stories?

Convert UI mockups into actionable user stories by analyzing the visual design to extract functional intent. The process identifies personas and scenarios, mapping them into a hierarchical Markdown format of steps and actions based on a functional graph guide.

What is the best way to translate visual design intent into product requirements?

The best way to translate visual design intent into product requirements is by extracting functional hierarchy from the UI. This approach converts visual elements into structured Markdown user stories, eliminating manual interpretation and ensuring alignment with design mockups.